Indirect prompt injection
AssessTechniques
An attack method where malicious instructions are hidden in external content an agent reads.
Why it's here
Placed in Assess: 1 article(s) of evidence from 1 source(s), led by product launches, with 1 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 7The New Stack·9/30/2026product_launchOpenAI Says Dots Boundary Issues Increased in Longer Task Chains
OpenAI reported that its new always-on Dots agents saw boundary-problem flags rise from 8.6% to 19.7% when chained tasks increased from five to ten in internal testing. The company says Dots use cloud computers, app connections, and layered permission controls, while its evaluations found no high-severity breaches or data exfiltration.